dshcode: Skill for Claude Code

.agents/skills/mansolo/SKILL.md

mansolo is a skill for Claude Code, Codex from whitelonng/dshcode. It costs 12 tokens per session (803 once invoked), scanned A, original, MIT.

A focused solo-execution workflow through mancode for small tasks or explicit handoffs. It keeps the work tied to the current task when governance is needed.

In plain words
What is it for?
Completing bounded development tasks independently or taking over an existing governed task.
Why use it?
Small tasks can become slowed by unnecessary coordination, while handed-off work can lose its context. This provides a focused path for either case.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is whitelonng/dshcode's own configuration. It tells Claude Code and Codex how to work on dshcode itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dshcode configures →

Reuse

Borrowing it

Nothing to install: this file belongs to whitelonng/dshcode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/whitelonng/dshcode/master/.agents/skills/mansolo/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/whitelonng/dshcode

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mansolo

README.md
[![agentmods](https://agentmods.dev/badge/skills/whitelonng/dshcode/mansolo.svg)](https://agentmods.dev/skills/whitelonng/dshcode/mansolo)
Your own site
<a href="https://agentmods.dev/skills/whitelonng/dshcode/mansolo"><img src="https://agentmods.dev/badge/skills/whitelonng/dshcode/mansolo.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00803
Opus 5 $0.00006 $0.00402
Sonnet 5 $0.00002 $0.00161
Haiku 4.5 $0.00001 $0.00080

Measured 3d ago against content hash b125a8174298, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mansolo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/mansolo/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mancode mode: mansolo

Purpose: perform a small focused task or accept an explicit solo handoff.

Enter through mancode

Before the first command, use ./node_modules/.bin/mancode when it exists, otherwise mancode; check that selected binary with --version once and never mix binaries or versions. In every command below, replace the literal mancode with that selected binary path when the local binary exists.

  1. Reuse a mancode status --brief --json snapshot already obtained in this conversation. Only when none exists, run it once from the project root. Never read or write legacy mode authority.
  2. If no governed task is being handed off, continue with focused solo work without creating a persistent mode, actor, session, or TaskRef.
  3. For an explicit governed handoff, ensure identity.actorId, reuse or create the current session, and bind the existing TaskRef. If status has no current session, reuse an explicit session ID already retained in this conversation. Only if neither exists, run mancode context session new --client codex in Codex, mancode context session new --client zcode in ZCode, or mancode context session new --client kimi-code in Kimi Code exactly once, then retain the returned session ID. Use --client codex in Codex, --client zcode in ZCode, or --client kimi-code in Kimi Code on every command that uses this session.
  4. For that governed task only, read mancode context show --purpose implement --session <id> --client <active-client> using the bound or explicit TaskRef.

Mode action

  • Do not create or persist a legacy solo mode. Ordinary focused work needs no TaskRef; if the operator expects a governed task, use its bound TaskRef or report that none is bound.
  • Read .mancode/shared/context/glossary.json when it exists and prefer its confirmed terms.
  • Before editing, assess both clarity and soundness using the project facts. If the request is clear, consistent, and low risk, proceed without ceremonial questions. Resolve repository-answerable unknowns yourself; classify the rest as blocking, recommendable, or defaultable. Ask and wait only when a blocking unknown could materially change behavior, scope, acceptance, data, security, compatibility, or ownership.
  • A supplied implementation direction is not automatically safe. If it conflicts with repository evidence or involves authentication, payment, sensitive data, deletion, migration, public APIs, untrusted input, concurrency, infrastructure, or another irreversible effect, show the evidence and impact, recommend the safer path, ask for focused confirmation, and wait before editing.
  • If resolving the ambiguity requires architecture, semantic owner/source-of-truth, cross-module scope, migration, team coordination, or formal acceptance decisions, recommend /man, explain the trigger, and wait for the operator to choose; advice alone never changes mode or authority.
  • Detect those governance triggers after the smallest fact check needed to establish them. Stop before exhaustive discovery or proposing a concrete topology, migration layout, or implementation plan that depends on unanswered decisions.
  • For a governed-to-solo transition, use mancode workflow handoff <namespace:ULID> --to solo --expected-revision <n> --session <id> --client <active-client>.

Read the full file on GitHub · 33 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 33 lines · 12 tokens per session scan A b125a8174298

Subscribe to this mod's changes

mansolo is a skill published in the GitHub repository whitelonng/dshcode (712 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 803 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

visionary-cli

Analyze images with DeepSeek's vision model via the visionary-server CLI. Use this whenever the user provides an image, photo, screenshot, or document with images - run vision to look at it rather than guessing.

xlight/deepseek-visionary · 46 tokens

openspec-archive-change

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

creativedswork/dscode · 31 tokens

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

commitment-setup

One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).

suyoumo/ClawProBench · 58 tokens

commitment-triage

Recognize obligations in conversation, extract signals with immediacy and expiration, create and manage commitments in the workspace.

suyoumo/ClawProBench · 29 tokens

linear

Linear issue tracker API integration. Covers first-use identity bootstrap (viewer + teams cached), raw GraphQL for list/search/create/update, and the rules for handling "my issues" / "assigned to me" requests.

suyoumo/ClawProBench · 45 tokens